Lune

EMNLP Findings2025

Capturing Latent Modal Association For Multimodal Entity Alignment

Yongquan Ji, Jingwei Cheng, Fu Zhang, Chenglong Lu

Abstract

Multimodal entity alignment aims to identify equivalent entities in heterogeneous knowledge graphs by leveraging complementary information from multiple modalities. However, existing methods often overlook the quality of input modality embeddings during modality interaction-such as missing modality generation, modal information transfer, modality fusion-which may inadvertently amplify noise propagation while suppressing discriminative feature representations. To address these issues, we propose a novel model-CLAMEA for capturing latent modal association for multimodal entity alignment. Specifically, we use a self-attention mechanism to enhance salient information while attenuating noise within individual modality embeddings. We design a dynamic modal attention flow fusion module to capture and balance latent intra-and inter-modal associations and generate fused modality embeddings. Based on both fused and available modalities, we adopt variational autoencoder (VAE) to generate high-quality embeddings for the missing modality. We use a cross-modal association extraction module to extract latent modal associations from the completed modality embeddings, further enhancing embedding quality. Experimental results on two real-world datasets demonstrate the effectiveness of our approach, which achieves an absolute 3.1% higher Hits@1 score than the sota method 1 .

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Tackling Uncertain Correspondences for Multi-Modal Entity Alignment cites Attribute-Consistent Knowledge Graph Representation Learning for Multi-Modal Entity Alignment
  • Tackling Uncertain Correspondences for Multi-Modal Entity Alignment cites Visual Pivoting for (Unsupervised) Entity Alignment
  • Attribute-Consistent Knowledge Graph Representation Learning for Multi-Modal Entity Alignment cites Knowledge Graph Alignment Network with Gated Multi-Hop Neighborhood Aggregation
  • Attribute-Consistent Knowledge Graph Representation Learning for Multi-Modal Entity Alignment cites Visual Pivoting for (Unsupervised) Entity Alignment
  • MEAformer: Multi-modal Entity Alignment Transformer for Meta Modality Hybrid cites Knowledge Graph Alignment Network with Gated Multi-Hop Neighborhood Aggregation
  • MEAformer: Multi-modal Entity Alignment Transformer for Meta Modality Hybrid cites Visual Pivoting for (Unsupervised) Entity Alignment
  • Visual Pivoting for (Unsupervised) Entity Alignment cites Knowledge Graph Alignment Network with Gated Multi-Hop Neighborhood Aggregation
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on8

  1. Knowledge Graph Alignment Network with Gated Multi-Hop Neighborhood AggregationZequn Sun, Chengming Wang, Wei Hu, Muhao Chen et al.AAAI 2020 · 379 citations
  2. Visual Pivoting for (Unsupervised) Entity AlignmentFangyu Liu, Muhao Chen, Dan Roth, Nigel CollierAAAI 2021 · 159 citations
  3. MEAformer: Multi-modal Entity Alignment Transformer for Meta Modality HybridZhuo Chen, Jiaoyan Chen, Wen Zhang, Lingbing Guo et al.ACM MM 2023 · 66 citations
  4. Attribute-Consistent Knowledge Graph Representation Learning for Multi-Modal Entity AlignmentQian Li, Shu Guo, Yangyifei Luo, Cheng Ji et al.WWW 2023 · 56 citations
  5. Tackling Uncertain Correspondences for Multi-Modal Entity AlignmentLiyi Chen, Ying Sun, Shengzhe Zhang, Yuyang Ye et al.NeurIPS 2024 · 20 citations

Related papers

  1. Cross-Modal Graph Attention Network for Entity AlignmentBaogui Xu, Chengjin Xu, Bing SuACM MM 2023 · 21 citations
  2. IBMEA: Exploring Variational Information Bottleneck for Multi-modal Entity AlignmentTaoyu Su, Jiawei Sheng, Shicheng Wang, Xinghua Zhang et al.ACM MM 2024 · 7 citations
  3. Multi-modal Siamese Network for Entity AlignmentLiyi Chen, Zhi Li, Tong Xu, Han Wu et al.KDD 2022 · 82 citations
  4. Enhancing Multi-Modal Entity Alignment via Multi-Grained Decision FusionYu Xing, Qizhuo Xie, You Lv, Ziyang Zhou et al.WWW 2026
  5. On Modality Weighting and Specificity for Multi-Modal Entity AlignmentYu Xing, Qizhuo Xie, Yunhui Liu, Qing Gu et al.AAAI 2026
Dusk over the sea between two cliffs drawn in fine vertical lines